ReFs: A hybrid pre-training paradigm for 3D medical image segmentation

Yutong Xie, Jianpeng Zhang, Lingqiao Liu, Hu Wang, Yiwen Ye, Johan Verjans, Yong Xia

Abstract: Highlights•The performance of self-supervised learning (SSL) on downstream tasks is hindered by a gap in representation.•ReFs uses reference tasks to steer SSL towards downstream-friendly directions.•Gradient matching enhances SSL and reference task compatibility, boosting ReFs.•ReFs outperforms SSL in downstream segmentation tasks, as shown by experiments.